Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Scandinavian verbs and sentence structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sensitively
    0.70
     collage
    0.68
    Quest
    0.66
     porn
    0.66
     calmly
    0.65
    aware
    0.65
     दादी
    0.65
     carried
    0.65
     constructively
    0.65
    Mord
    0.65
    POSITIVE LOGITS
     blir
    1.41
     bliver
    1.41
     går
    1.35
     står
    1.34
     ligger
    1.34
     får
    1.29
     kan
    1.29
     är
    1.28
     kommer
    1.26
     består
    1.15
    Act Density 0.032%

    No Known Activations